NOUMENOpen app
NOUMEN

xAI · Frontier

Grok 4.6

Added Aug 12, 2026

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Use in the app

Grok 4.6 is SpaceXAI's frontier reasoning model for coding, knowledge work, and STEM. It supports text, image, and file inputs with tool calling and structured outputs. Reasoning is always active, and requests above 200k input tokens use higher long-context rates. Content policy rejections can still be charged: SpaceXAI may pass through a $0.05 moderation-failure fee, or a $0.055 usage-guidelines violation fee, depending on which rejection upstream returns.

  • Reasoning
  • Tools
  • Vision
  • Structured output
Input
Text, Images
Output
Text
Reasoning effort
low · medium · high · xhigh
Discovery tier
Frontier

Pricing

USD per 1M tokens
Input
$2.00
Output
$6.00
Cache read
$0.50

Reference prices as published by the model provider. API example

Specifications

Context window
500K
Max output
—
Average output (7 days)
1.8K tokens
Longer than 89% of 473 models

Side by side

Grok 4.6 compared

Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Grok 4.6xAIThis modelGrok Build 0.1xAIRemove
ProviderxAIxAI
Discovery tierFrontierBalanced
AddedAug 12, 2026May 20, 2026
Limits
Context window500KBest256K
Average output1.8K tokens3K tokens
Pricing, USD per 1M tokens
Input$2.00$1.00Best
Output$6.00$2.00Best
Cache read$0.50$0.20Best
Performance
Throughput155.2 tok/s—
Time to first token3.0 s—
Request success (24h)100.0%—
Benchmark indexes
Intelligence Index44.3Best27.2
Coding Index76.8Best51.5
Capabilities
ReasoningYesYes
ToolsYesYes
VisionYesYes
Structured outputYesYes
Reasoning effortlow, medium, high, xhigh—

Public evaluations

Benchmarks

Independent evaluation results, with how each score ranks among the models in the Noumen catalog.

  • Grok 4.6
  • Grok Build 0.1

Intelligence Index

  • Grok 4.644.3
  • Grok Build 0.127.2

Grok 4.6 tested at high reasoning effort

Grok 4.6: Better than 90% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Grok 4.6: 76.8Top
    • Grok Build 0.1: 51.5

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Grok 4.6: 66.7%
    • Grok Build 0.1: —

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Grok 4.6: 32.7%
    • Grok Build 0.1: —

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Grok 4.6: 1,531 Elo
    • Grok Build 0.1: —

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Grok 4.6: 1,618 EloTop
    • Grok Build 0.1: 1,065 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Grok 4.6: 17.0%
    • Grok Build 0.1: —

  • AA-LCRv1.1

    Reasoning across long documents

    • Grok 4.6: 80.3%Top
    • Grok Build 0.1: 74.7%

  • MLCR-AA

    Long-context reasoning over medical records

    • Grok 4.6: 15.6%
    • Grok Build 0.1: —

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Grok 4.6: 42.9%Top
    • Grok Build 0.1: 38.3%

  • GPQA Diamond

    Graduate-level science questions

    • Grok 4.6: 94.9%Top
    • Grok Build 0.1: 89.5%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Grok 4.6: 21.2%
    • Grok Build 0.1: —

  • SciCode

    Scientific computing in Python

    • Grok 4.6: 56.5%
    • Grok Build 0.1: —

Legacy evaluations

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Grok 4.6: 80.3%Top
    • Grok Build 0.1: 74.7%

Scores from Artificial Analysis, updated Oct 26, 2026. Grok 4.6 was tested at high reasoning effort; compare scores measured at the same effort.Artificial Analysis

Live routing data

Performance and reliability

Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.

Throughput
155.2 tok/s
Faster than 76% of 256 models
Time to first token
3.0 s
Quicker than 51% of 256 models
Prompt cache hits
85.2%
About $0.72 per 1M input tokens with caching
Request success (24h)
100.0%
Reliable

Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.

Hourly request success · last 72 hoursLowest hour 96.4%
  • Healthy (98% or more)
  • Degraded (90–98%)
  • Down (under 90%)
  • No requests

Developers

Use it through the API

Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.

Read the quickstart
curl https://www.noumen.xyz/api/v1/chat/completions \
  -H "Authorization: Bearer $NOUMEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "x-ai/grok-4.6",
    "reasoning_effort": "medium",
    "messages": [{ "role": "user", "content": "Explain this stack trace." }]
  }'
import os
from openai import OpenAI

client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
    model="x-ai/grok-4.6",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

xAI

Other xAI models, starting with the same family.